电子学报 ›› 2014, Vol. 42 ›› Issue (7): 1299-1304.DOI: 10.3969/j.issn.0372-2112.2014.07.009

• 学术论文 • 上一篇    下一篇

基于投影的稀疏表示与非局部正则化图像复原方法

徐焕宇1, 孙权森2, 李大禹1, 宣丽1   

  1. 1. 中国科学院长春光学精密机械与物理研究所应用光学国家重点实验室, 吉林长春 130033;
    2. 南京理工大学计算机学院, 江苏南京 210094
  • 收稿日期:2012-11-29 修回日期:2014-01-20 出版日期:2014-07-25
    • 作者简介:
    • 徐焕宇 男.1985年3月出生,吉林吉林人.2008年、2013年分别在南京理工大学获得工学学士、工学博士学位,现在中国科学院长春光学精密机械与物理研究所任助理研究员,研究方向为图像处理、自适应光学.E-mail:xhydtc@hotmail.com;孙权森 男.1963年11月出生,山东梁山人,教授、博士生导师.2006年于南京理工大学获得工学博士学位,现任职于南京理工大学计算机科学与技术学院,主要研究方向为模式识别与图像处理.E-mail:qssun@126.com
    • 基金资助:
    • 国家自然科学基金 (No.61273251,No.11174274,No.11174279,No.61205021,No.11204299,No.61377032,No.61378075)

Projection-Based Image Restoration via Sparse Representation and Nonlocal Regularization

XU Huan-yu1, SUN Quan-sen2, LI Da-yu1, XUAN Li1   

  1. 1. State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, Jilin130033, China;
    2. School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China
  • Received:2012-11-29 Revised:2014-01-20 Online:2014-07-25 Published:2014-07-25
    • Supported by:
    • National Natural Science Foundation of China (No.61273251, No.11174274, No.11174279, No.61205021, No.11204299, No.61377032, No.61378075)

摘要:

提出一种基于投影的稀疏表示与非局部正则化相结合的图像去模糊、去噪图像复原方法.该方法结合了自适应构造字典的稀疏表示与非局部总变差,提出的正则化模型分解为三个投影子问题进行求解以提高求解效率.实验结果表明,本文所提出的图像复原方法能够有效地保持原图像的纹理细节信息,对于不同程度的退化图像上均有较好的复原结果,在视觉效果和客观评价指标上均优于相比较的现有方法.

关键词: 图像复原, 稀疏表示, 非局部总变差, 正则化

Abstract:

This paper proposes a projection based sparse representation and nonlocal regularization deblurring and denoising image restoration algorithm.The algorithm combines sparse representation via adaptive learned dictionary and nonlocal total variation,and the proposed regularization model is divided into three projection sub problems to solve to improve the efficiency.Experimental results show that the proposed algorithm can preserve the detail information effectively,and have nice restoration results for images with different degree of degradation.The proposed algorithm achieves improvement on both visual appearance and objective indices compared with state-of-the-art methods.

Key words: image restoration, sparse representation, nonlocal total variation, regularization

中图分类号: